Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/theafh/ai-modulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/theafh/ai-modules/ai_dev)<a href="https://agentmods.dev/plugins/theafh/ai-modules/ai_dev"><img src="https://agentmods.dev/badge/plugins/theafh/ai-modules/ai_dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/theafh/ai-modules/ai_dev"><img src="https://agentmods.dev/badge/plugins/theafh/ai-modules/ai_dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ai_dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "ai_dev",
"version": "1.16.1",
"description": "Skills and agents for everyday AI-assisted development: structured git commits, checkout of an existing branch wherever it lives, safe repository refresh and branch cleanup, review of a pull request, a branch, or uncommitted default-branch changes for approvability and structural mergeability, an automated review-and-fix loop over that same default-branch uncommitted target (git_auto_review, whose auto_gate_git gate, auto_fixer_git writer, and auto_verifier_git verifier run it), day-grouped changelog maintenance, project-local task and todo tracking as plain-markdown files (a base task skill plus create, check, auto-check, explain, select, implement, audit, finish, and fix siblings with auto_*_task helper agents, including task_auto_check's auto_drift_task intent check and auto_dryrun_task pre-gate implementer dry run, and task_fix's auto_shaper_task escalation), repo-root guardrail documents that keep autonomous agents anchored to human intent (a guardrail hub skill plus a guardrail_audit sibling, with per-type templates and rules for CHARTER, ARCHITECTURE, TESTING, and SECURITY docs), writing and formatting AI instructions (prompts, rules, skill files, agent definitions), skill_doctor for check-only audits of skill artifacts, descriptions, registration, and tests, agent_spinner for how an orchestrating agent spins off, contains, cross-checks, and aggregates helper agents on any host, harness portability for bundled scripts and plugin wiring, and language style guides for markdown, Python, and Rust.",
"author": {
"name": "Andreas F. Hoffmann"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 26 skills, 9 agents, 1 hook travel with it, and installing the plugin installs all of them — 3,407 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill task A 100 tokens
- Skill task_auto_check A 91 tokens
- Skill git_auto_review A 131 tokens
- Skill ai_instruction_formatting A 142 tokens
- Skill format_python A 72 tokens
- Skill git_review A 207 tokens
- Skill agent_spinner A 255 tokens
- Skill guardrail A 182 tokens
- Skill harness_portability A 157 tokens
- Skill skill_doctor A 105 tokens
- Skill task_fix A 98 tokens
- Skill git_commit A 102 tokens
- Skill task_implement A 52 tokens
- Skill update_changelog A 61 tokens
- Skill ai_instruction_writing A 87 tokens
- Skill guardrail_audit A 156 tokens
- Skill task_audit A 62 tokens
- Skill task_check A 77 tokens
- Skill task_create A 58 tokens
- Skill task_select A 55 tokens
- Skill git_checkout A 175 tokens
- Skill task_finish A 50 tokens
- Skill format_rust A 87 tokens
- Skill git_refresh A 127 tokens
- Skill task_explain A 82 tokens
- Skill format_markdown A 62 tokens
- Agent auto_gate_task A 0 tokens
- Agent auto_verifier_task A 91 tokens
- Agent auto_dryrun_task A 0 tokens
- Agent auto_drift_task A 50 tokens
- Agent auto_gate_git A 160 tokens
- Agent auto_fixer_git A 127 tokens
- Agent auto_reviewer_task A 37 tokens
- Agent auto_verifier_git A 109 tokens
- Agent auto_shaper_task A 0 tokens
- Hook PreToolUse A not measured
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed f95ad69145f6
- yesterday Changed 1e67e50d3a7d
- 2d ago Changed 7be1422bf7d5
- 4d ago Changed f3ca29e0c6a8
- 5d ago Changed 2eec63ca71cf
- 6d ago Changed 2e083c047403
- 7d ago Changed ef0f1e3ffd5e
- 10d ago Changed 9449954dfbe1
- 11d ago Changed afaba21719b7
- 14d ago First seen · 10 lines scan A 78d6db624dd7
ai_dev is a plugin published in the GitHub repository theafh/ai-modules (38 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
git-sidebar
A lazygit-style side pane: every worktree of the repository and its local branches as rows you click. A worktree row moves the session there with /cd; a branch row shows its last commits and offers switch (clean tree only) or open worktree. Docked floor to ceiling beside the transcript in the fullscreen layout, above…
git
Git workflow tools: commits, PRs, review inbox, checkout, and work triage.
digest
Summarize AI-generated branches, PRs, and diffs into icon-rich cards, explain code state with git archaeology as self-contained HTML explainers, plus multi-project weekly recall digests.
git-pr
Committing, PR creation and review triage, and dependency upgrades.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
feature-to-pr-factory
Turn one feature into dependency-ordered GitHub or GitLab issues, then build each ticket into its own reviewed, tested, stacked PR or MR with agents.